© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-2B
    5. 24-GEMMASCOPE-TRANSCODER-16K
    7. 14776
    Prev
    Next
    INDEX
    Explanations

    words that are part of a set of rules

    oai_token-act-pair · gemini-2.0-flash

    Minecraft/server applications

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_24/width_16k/average_l0_37
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.24.ln2.hook_normalized
    Architecture
    jumprelu_transcoder
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    LEncoder
    -0.65
    SocketChannel
    -0.57
    MethodManager
    -0.56
    Marshal
    -0.55
    EndGlobalSection
    -0.52
    quema
    -0.52
    creativecommons
    -0.51
    IonicModule
    -0.51
    Спољашње
    -0.51
    httphttps
    -0.51
    POSITIVE LOGITS
    تقاوى
    0.63
     CURIAM
    0.60
    Filler
    0.59
     continuant
    0.53
    IsContent
    0.52
    //
    0.51
    Portale
    0.49
    DoubleQuotes
    0.49
     Op
    0.48
    ็จ
    0.48
    Activations Density 2.139%

    No Known Activations